Related Experiment Video
Updated: Sep 20, 2025
11:16
Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
Published on: July 22, 2014
16.4K
Real-Time Gait Phase Detection Using Wearable Sensors for Transtibial Prosthesis Based on a kNN Algorithm.
Atcharawan Rattanasak1, Peerapong Uthansakul1, Monthippa Uthansakul1
1School of Telecommunication Engineering, Institute of Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, Thailand.
Sensors (Basel, Switzerland)
|June 10, 2022
Summary
This study introduces a new insole sensor system that uses the k-nearest neighbor (kNN) algorithm to detect walking phases for prosthetic leg control. This innovation significantly improves prosthetic function and wearer mobility.
Area of Science:
- Biomedical Engineering
- Rehabilitation Technology
- Wearable Sensors
Background:
- Traditional prosthetic legs lack advanced control mechanisms, limiting natural gait and mobility for amputees.
- Existing prostheses often fail to adapt to the wearer's specific walking patterns, causing discomfort and inefficiency.
- Developing intelligent control systems is crucial for enhancing the functionality of lower-limb prosthetics.
Purpose of the Study:
- To develop an insole device with wearable sensors for real-time gait phase detection.
- To utilize the k-nearest neighbor (kNN) algorithm for accurate prediction of walking phases.
- To enable effective control of transtibial prosthetics based on detected gait phases.
Main Methods:
- An insole device equipped with pressure sensors was designed and implemented.
- The k-nearest neighbor (kNN) algorithm was employed to analyze sensor data for gait phase recognition.
- Seven distinct walking phases (stand, heel strike, foot flat, midstance, heel off, toe-off, swing) were identified.
- The system was tested for its ability to control transtibial prosthesis ankle movement.
Main Results:
- The kNN algorithm achieved 81.43% accuracy in gait phase detection.
- The developed insole system effectively controlled the transtibial prosthesis at walking speeds up to 6 km/h.
- The system demonstrated improved predictive accuracy with continued use, adapting to individual gaits.
- The insole device is characterized by its small size, light weight, and independence from wearer's physical factors.
Conclusions:
- The sensor-equipped insole device provides an effective solution for real-time gait phase detection in transtibial prosthesis users.
- The kNN algorithm offers a robust method for predicting walking phases, enabling adaptive prosthetic control.
- This technology has the potential to significantly improve the mobility and quality of life for individuals with leg amputations.
